Junior Kelly Young spent last summer tracking algae blooms from 438 miles in the air, via NASA’s Landsat 8 satellite, to learn more about when and where they happen.

Algae blooms occur when run-off drags excess fertilizer into bodies of water, providing the aquatic plant with abundant nutrients. Their population grows exponentially, and they consume all or most of the oxygen in the water. This creates a detrimental effect on the local ecosystem, often called a dead zone, where no life can prosper.

NASA provides open access to Landsat data so scientists can use it. Young believes that with more data on algae blooms, she can help predict and restrain their overgrowth.

“Once the blooms form, it’s really hard to get rid of them or decrease the effect that they have on the environment,” says Young, a double major in environmental studies and geography. “The goal is to be able to create a model to predict where the blooms are going to form and when they are going to form, so we are able to alert local agencies to better prevent the blooms from becoming full blown.”

Every 16 days, a satellite passes over New York’s Chautauqua Lake and Seneca Lake, measuring several ranges of light frequencies, called bands. Landsat 8 measures 11 bands, with only four of them being visible to the naked human eye.

But algae blooms in some lakes are so dense it doesn’t take a high-tech satellite to find them.

“In the summer the algae concentrations are very high so you visibly see it,” Young says. “So on an average day in the summer, if someone is walking by one of these lakes, they will be able to see the algae in a thick green color.”

Young developed a data-processing algorithm, which found that in these lakes harmful algae blooms are mainly focused in the southern basins between May and August. Findings like this help her research group narrow down the timing and location of algae blooms so eventually they can use drones to pick up more detailed readings.

Young says while Landsat data is a necessary beginning for creating a predictive model, there are some major faults that drones could fix.

“When I processed [the Landsat data] for chlorophyll, I found that some months that shouldn’t have a high concentration have a high concentration,” Young says. “That’s because the clouds distort the satellite and the data.”

Young’s research, which was funded by Binghamton University’s Summer Scholars and Artists program, received recognition on campus and beyond.

During the University’s November Geographic Information System (GIS) Day celebration, Kelly’s work won first place in the undergraduate poster competition. She also was invited to present her findings at the 2019 American Geophysical Union’s annual meeting in San Francisco.

Timothy De Smet, director of Binghamton University’s Geophysics and Remote Sensing Laboratory, mentored Young throughout her summer research. He says her findings are vital in the continuation of algae bloom research, and that her inner drive is what led to the project’s success.

“She is extremely hardworking, whether it be as a campus tour guide, in class or on her research,” De Smet says. “She is smart, obviously, but also resilient — you need that grit to make it in research.”

This is not Young’s first experience researching algae; in her Brooklyn high school, she experimented using barley straw to decrease toxicity in algae. She also participated in the First-year Research Immersion program, where her group used drones.

Brianna Sander studied the long-term effects of microplastics on host-parasite interactions in wetlands as a 2019 Summer Scholar at Binghamton University.

Microplastics originate from larger plastic products, like polyester clothing, that deteriorate into pieces and fibers smaller than 5 millimeters long. Surveyors have found the microscopic plastic in many bodies of water and even in bottled drinking water.

“With plastic pollution it is easy to think about the immediate effects — organisms ingesting it and facing health effects, stress effects,” says Sander, a senior majoring in biological sciences. “But the next type of question we can ask is, ‘Yes, we acknowledge plastics are going to be in our ecosystems for a long time, so how does their presence affect other long-standing relationships?’”

To answer this question, Sander tested two groups of tadpoles: one exposed to polyester fibers less than 1 millimeter long for 24 hours and then exposed to the parasites, and another group of hosts exposed to parasites and microplastics simultaneously for 24 hours.

Her results showed the exposure negatively affected the second group of parasites and their ability to infect the host. Although this may seem like a positive, as it would save tadpoles, it could also throw off the local ecological balance and negatively affect other populations.

Sander has already started thinking about how to take the study further. For instance, another study could involve exposing both parasite and host for a longer time.

After joining Jessica Hua’s wetlands lab as a sophomore, Sander worked with the assistant professor of biology for over a year helping to research similar relationships, but with a focus on chemical stressors instead of microplastics. Although this experience gave her a solid foundation, Sander needed to branch away from the lab’s history to pursue her research questions.

“I think something that is key in her research is that this is a new direction in my lab,” Hua says. “It took a lot of independence and passion from Bri to bring it about, and a lot of dedication because it meant she had to do a lot of background research so she could actually ask the type of questions she did for this study.”

Sander’s interest in microplastics came after she realized there was a major hole in how the contaminant was studied.

“What exists right now are experiments and research concerning the immediate health effects from the ingestion of microplastics and larger plastic materials, and the other half is surveys looking at what is in our environments,” Sander says. “I was noticing a huge gap in knowledge surrounding microplastics. When I pitched it to Jess, her eyes kind of lit up because she hadn’t thought of it before.”

Sander deliberated for a month between plastics, but she ultimately chose polyester microfibers due to their prominence in human products and many samples of water.

“When I was figuring out where these microfibers came from, I was just sitting in my lab and wanted to look at one under a microscope,” Sander says. “I realized the jacket I was wearing was 100% polyester, so I ripped a string out. That is when I realized that almost everything is made of plastic.”

Sander’s curiosity to look deeper into microfibers is rooted in her passion for science as well as her love of art. By combining the two, she created an Instagram account, @Bri_On_Earth, visually showcasing her experiences with nature in addition to a brief scientific explanation.

Sander wants to focus her future studies on marine biology, and she says her dream job would combine marine biology with art.

While growing up in Rocky Point, Long Island, Sander was mesmerized by the amount of wildlife just in her backyard. Although science has intrigued her since childhood, Sander knows not everyone had the same experience. She says art is the perfect way to involve more people in science.

“For my friends that aren’t in the sciences, they think I am some crazy scientist,” she says. “But little do they know that just them reading my Instagram captions is them engaging in science as well.”

Binghamton University now boasts a No. 1 ranking in sustainability research from the Association for the Advancement of Sustainability in Higher Education (AASHE).

The campus is part of a five-way tie with Florida State University; University of California, Irvine; UC Merced and UC San Diego, which each earned a score of more than 100 percent.

Jessica Hua, an assistant professor of biology, says although she is not surprised Binghamton ranks at the top for sustainability research, she is glad her community is getting the recognition it deserves.

“I think we know that we have committed people here doing research on this topic that work so hard, so to get that recognition is fantastic,” Hua says. “It wasn’t on my radar, but in terms of the quality of research I am not surprised at all. My colleagues are incredible.”

AASHE ranks universities in 17 different subsets of sustainability based on self-reports. The research subset score is derived from the amount of research on sustainability, as counted by number of faculty and departments.

Binghamton’s report shows that of 601 faculty and staff who conduct research, 156 of them focus on sustainability. That 25.96 percent brought the campus well over the 15 percent needed for a perfect score.

The report also shows 42 departments have at least one faculty member who conducts research. Of the 42, 34 of them have at least one who conducts sustainability research. The 80.85 percent score also tops the “perfect” mark of 75 percent.

To put a spotlight on key subjects, the University created five Transdisciplinary Areas of Excellence (TAEs) in 2013. One of the TAEs focuses on Sustainable Communities. Carl Lipo, director of environmental studies, and Robert Holahan, associate professor in environmental studies, co-chair the TAE and bring faculty together from several departments.

“The TAE’s goal has always been to bring people from across campus with a similar research interest together,” Holahan says. “There’s 10 of us from the TAE who got together and have been working on a series of papers on sustainable communities. Without having a centralized foci, a place to go once a week, how are you going to meet those people?”

In addition to sparking research collaborations, the TAE also awards seed grants to support research and hosts a sustainability lecture series. A dozen faculty and staff members make up the TAE’s steering committee; about 30 people receive the group’s newsletter.

Hua, who participates in the TAE, runs a research lab focused on wetlands ecology and conservation. Much of the lab’s research looks at artificial stressors on populations, such as the effect of road salt on amphibians.

Hua says conservation research findings need to be presented in a way that the general public can understand.

“I think how we link conservation and sustainability in our research is really through education,” she says. “What that means to me is to link art and science through art shows that tell the story of our publications, children’s books to get kids interested in ecology and parasite ecology, things like card games and lesson plans for K through 12 educators.”

Binghamton’s proposed Nuthatch Hollow Living Building is another signature effort in sustainability. Besides being a center for sustainability education, the University also aims for it to be one of the few in the world to meet the Living Building Challenge standards, which require buildings to produce more energy than they use.

Mark Poliks, chair of the Smart Energy TAE, says research and innovations in smart energy are building blocks to a sustainable future and projects like the living building.

“The Smart Energy TAE is really involved in the technology that could eventually go into a learning building, or go into a facility where energy is being managed, energy is being harvested or energy is being stored,” Poliks says.

Faculty members associated with the Smart Energy TAE fit into four broad areas: solar and thermoelectric energy harvesting, energy storage, energy efficiency in electronic systems and sensor development for energy resource management. Some researchers in this group are looking at battery efficiency and alternative energy harvesting, like solar cells, to provide a more sustainable future.

“More and more homes are having solar on it, and as the technology gets upgraded it will be both safe and affordable to have an appropriate battery pack in the house so that you can power the house in the evening and not have to rely on the grid,” Poliks says.

Lipo says Binghamton’s attention to sustainability helped him decide to come to work here four years ago. Now, he says, the AASHE ranking will promote the idea even more.

“We want our campus to be known for sustainability,” Lipo says. “This recognition will attract even more students and faculty who are passionate about sustainability and we will continue to grow in that regard.”

Dana Bani-Hani, a doctoral student studying industrial and systems engineering, has spent the past few years teaching machines how to read data sets in any industry. The system she coded, called a Recursive General Regression Neural Network Oracle (R-GRNN Oracle), takes data inputs and creates prediction outputs.

Classification models are not new in data science and analytics, but what Bani-Hani created goes beyond the basics. A typical system uses algorithms, called classifiers, that run through a data set of many different variables to create a prediction. Oracles are created to run multiple sets of these classifiers to see which algorithm creates the most accurate prediction.

For example, a classifier can look at a myriad of emails and factor in certain word usage, word count and several other variables to determine if the email is spam. An oracle looks at the different classifier outputs and determines which most accurately predicted the spam emails.

What sets the R-GRNN Oracle apart from other oracles is its capability to take classifier outputs and rank them based on their accuracy. Based on the ranking, classifiers are given weights and are combined to produce a prediction superior to any one classifier on its own.

Think of this process like an orchestra. Each instrument has its own strengths, just like different classifiers, so it is useful to include them all. The conductor, like the R-GRNN Oracle, directs the different instruments to play loudly or more softly based on how the instrument makes the final symphony sound.

At this point, the system would be called a General Regression Neural Network (GRNN), which has been created before at Binghamton University. The real crux of Bani-Hani’s work lies in the first letter, R, standing for Recursion.

The R-GRNN Oracle takes the original GRNN output, and uses that entire system as an input for another GRNN prediction. This is combined with the most successful of the original classifiers.

So, back to the orchestra: The original symphony is recorded, and then played back again later. This time, along with the recording, a few instruments play again to further fine-tune the important sounds of the orchestra.

“Because of the way [the GRNN] works, I was able to create the recursive model,” Bani-Hani says. “The concept of recursion is not widely used in machine learning, so I decided to put an oracle inside of an oracle.”

Mohammad Khasawneh, professor and department chair in systems science and industrial engineering, supervised Bani-Hani’s research. He says systems like the GRNN and R-GRNN are underutilized and are vital in serious life events.

“The traditional GRNN Oracle has received limited attention in the literature as only very few researchers have published work on the algorithm,” Khasawneh says. “But many real-life problems that apply machine learning models to automate classifying unknown observations require accurate predictions. Tasks such as diagnosing diseases entail precision to avoid serious issues that could potentially lead to problems such as lawsuits or even deaths.”

Bani-Hani says the R-GRNN Oracle produces more accurate predictions than any single classifier alone, as well as one GRNN on its own. The R-GRNN Oracle took in thousands of email samples, programmed to factor 57 variables, and then produced a spam prediction superior to all other classifiers tested.

Bani-Hani also used the R-GRNN to predict credit card application fraud, diabetes diagnosis and whether a worker will quit based on past workplace experiences. In each case, the R-GRNN came out as the most accurate predictor.

She plans to focus her model on specific fields, such as business or finance, as well as package both the GRNN Oracle and the R-GRNN Oracle so companies do not have to create the entire code from scratch.

Bani-Hani’s journey to machine learning research started nearly 6,000 miles away from Binghamton in Jordan. After completing her bachelor’s degree in architectural engineering, she heard about Binghamton University through Watson School faculty and academic leaders, and from her father’s supportive suggestions. She initially pursued a master’s degree in industrial engineering, but she soon found a new passion: data mining and machine learning.

“Getting a PhD has been a dream of mine for the last 15 years,” Bani-Hani says. “I mainly attribute this to having a family with advanced degrees. I am thankful to my professors here at Binghamton University for introducing me to the topics that make up my research.”

Wenna Duan, a doctoral student in computer science, uses magnetization transfer rate (MTR) as a visual biomarker for brain tissue health.

MTR is a measurement most commonly used in magnetic resonance imaging (MRI) when looking at the brain. An MRI shoots energy into tissue cells, disorienting them, and then is turned off. MTR measures the amount of time the tissue cells take to dissipate the energy and reorient themselves.

Duan determined that brain tissue, specifically white matter, dissipates the energy more slowly in a brain that is more likely to suffer from Alzheimer’s. By comparing the MTR of brains suffering from different stages of Alzheimer’s with undiagnosed scans, doctors would be able to diagnose before the patient suffers from symptoms such as memory loss.

It’s a potentially vital development in the fight against Alzheimer’s disease, which the Centers for Disease Control and Prevention reported led to the deaths of more than 120,000 Americans in 2017.

The International Society for Magnetic Resonance in Medicine (ISMRM) accepted Duan’s research for its 2019 annual conference, where it received a magna cum laude award, which is given to the top 15% of thousands of projects.

The process of comparing scans was not a quick one. Duan had to create a template made up from the average of thousands of scans from a specific stage of Alzheimer’s. Then, because brain shape and size varies, she had to manipulate the undiagnosed scans, one by one, to fit the size of the template.

“The most challenging part of it all was in the preprocessing, especially because I had to teach myself the science behind the data to use it,” Duan says. “It took around two months to process all of the brain scans, and there were some very late nights.”

The brain data was collected as both longitudinal, where one subject was observed over several years, and cross-sectional, where one time-point was observed in different stages of Alzheimer’s, by the Cardiovascular Health Study at the University of Pittsburgh.

Weiying Dai, an assistant professor of computer science who previously taught at the University of Pittsburgh, supervised Duan’s research at Binghamton and provided the database. Dai says Duan’s research has the potential to make big changes in the clinical field.

“Her research can also help to identify potential treatment groups when a new drug comes to play as we do not currently have a cure for Alzeihmer’s,” Dai says. “Her work is clearly application oriented. If successful, she will make a huge contribution to both method development and clinical application.”

Duan is continuing her research with hopes of reconfirming her findings until this process is used regularly to help patients.

Her collaboration with Dai began when she took a machine learning course Dai taught.

“I did research with her and didn’t know it was all MR related, but when I turned in the MR project, she introduced how significant those findings are in the clinical area,” Duan says. “I thought, ‘You are really impacting somebody,’ so I got very excited and I decided to continue with that.”